Click any tag below to further narrow down your results
Links
This is ChatGPT's help doc on giving your "dot" (a cloud-based assistant) its own cloud computer, access to your local machine, and permission to use your apps and websites. It covers how to connect, what access each step grants, and how logins and sessions are handled.
- The dot runs on its own cloud computer with separate files, software, and browser sessions, so it keeps working when your own machine is off, and signing in on your computer doesn't sign the dot in anywhere.
- Connecting a local computer is a separate permission from Codex or Work Sync, and it persists until you revoke it. An Offline status pauses access but doesn't remove it.
- Website logins go through a private form sent to the remote browser outside the chat, and saved logins are optional and need your confirmation to reuse. Saved logins and active sessions are treated as different things.
- App access is scoped per plugin and per permission, so you can let the dot read Gmail without letting it send email. Messaging the dot through a channel like Slack doesn't connect your inbox.
Sean Goedecke built AutoDeck, an app that generates an endless feed of spaced repetition flashcards on any topic with an LLM, adjusting difficulty from the user's responses. He uses it to explain why he skipped the chat interface and what building it with Codex was like.
- Generating flashcards is the hard part of spaced repetition for new topics, and LLMs make it possible to create decks on demand.
- Parallel generation produced duplicate cards, and waiting for one batch was slow, so he streamed cards in XML chunks as each was generated, since JSON can't be parsed mid-stream.
- Codex did most of the coding but made bad calls he had to fix, such as over-engineering a background job system and tracking cards by index instead of ID; he found Claude Code slower and needing more intervention.
- Paid inference costs pushed him to charge for the app, which he thinks made him build something more useful than a free side project would have been.
The author describes how juggling 20 parallel Claude Code or Codex threads wore out their focus, so they built a system where tickets live as markdown in git, an agent works the board in cycles, and the author only handles a prioritised inbox of items needing human judgement. Each ticket is closed out when it is decided, so context does not pile up in memory.
- The core problems are sequencing and context: running many agent threads at once overloads working memory, and the author treats that as the real failure mode.
- The agent researches, builds safe tickets, runs tests and browser checks, and works on branches for sensitive code, but never deploys to production. The human keeps that step and every judgement call.
- Each ticket is closed by writing the verdict back into git and returning the item to the queue, so only one decision is open at a time. The author says it is still tiring but no longer leaves them distracted or lost.
OpenAI is buying Pierre Computer Company, the small team behind the Trees and Diffs libraries already used inside the Codex app and the Code Storage service for storing code under Git. The goal is to build Git workflows suited to coding agents, with the deal still subject to regulatory approval.
- Pierre's Trees and Diffs libraries are already used in Codex for browsing files and reviewing changes, and Diffs includes an Edit mode for fixing lines directly in a review.
- Pierre also built Highlights, a fast syntax highlighter that updates as code is typed or streamed from an agent, and designed the API for Code Storage.
- Open-source Pierre projects stay open-source, Code Storage remains available to existing customers while its features move into Codex, and the two companies stay separate until the deal closes.
Conductor, the agent workspace tool, is being acquired by Meta, so its cloud service goes read-only on November 13 and shuts down on November 20. The local Mac app keeps getting model updates and bug fixes until early 2027, and this release also adds custom completion sounds and several UI fixes.
- Conductor Cloud goes read-only on November 13 and shuts down on November 20, so cloud users need to move their work soon.
- You can transfer a cloud workspace and its chats to your Mac by right-clicking it and choosing Transfer to local, or export all data from Settings → Account.
- The local Conductor app gets new models and critical fixes until early 2027.
OpenAI is folding the Chat and Work tabs in the ChatGPT desktop app into one screen, so you can go from idea to finished output without switching modes. Codex stays separate, and chat and Codex will draw from a shared token pool.
- The Chat and Work tabs are being merged, starting with a limited group of users for feedback before a wider rollout.
- You can bring in files and plugins and have ChatGPT build a website, make a presentation, or act on the web while you review its work.
- ChatGPT and Codex will share one token allowance, which OpenAI says won't affect most users, though heavy users may hit limits and wait for resets more often.
The author argues that as AI coding agents write more of the software, engineers need less of a hand-built mental model of every line and more of a high-level map of their systems, plus the ability to dive into any part when something breaks. He says the old path of learning by writing and debugging by hand isn't economically viable for juniors, so the industry needs a different way to build that understanding.
- A coding agent (Codex) packed about 15 React components onto single lines and produced complex logic that tripped SonarQube's cyclomatic complexity check; the author reviewed it, found the complexity justified, and had the agent split it into 10 files.
- Traditional ownership of a system came from years of writing, reading, and debugging code by hand. Agents break that link because code now often never passes through a human's hands.
- Both camps are wrong: "read every line" doesn't scale and companies won't fund juniors to learn by hand, while "don't look at the code" leaves owners unable to handle production failures.
- The proposed path is fundamentals plus breadth: a working map of system abstractions and failure modes, with just-in-time depth where the monsters actually live.
Hallmark is an open-source skill for Claude Code, Codex, Cursor and OpenCode that builds web pages from fifty selectable design materials and lints the output for telltale AI design patterns. It checks rendered pages against a set of hard requirements and reflex defaults before a page ships.
- It deals three themes from a catalog of fifty, each a material with its own palette, type, and components, and builds the page around what the visitor came to do.
- A lint script (sloplint) checks the page in a real browser at eight widths for tells like eyebrow labels, empty frames, and fake form confirmations, then a fresh-context subagent reviews it.
- Redesign and audit modes keep existing content and wiring intact, with checks that fail if a link, field, or handler goes missing.
Tomarigi is a macOS app that visualizes Claude and Codex coding agent sessions as animated birds in a floating window, letting you monitor multiple agents' status at a glance and jump between their terminal panes. It reads session transcripts directly without requiring hooks or config changes, and optionally uses API keys for speech summaries and question detection.
- Displays each AI coding session as a bird with status indicators (working, waiting, done) in an always-on-top floating window that's click-through to windows below
- Works passively by reading existing transcript files from ~/.claude/projects and ~/.codex/sessions with no agent-side modifications needed
- Integrates with Ghostty terminal to jump directly to the pane running a specific session with one click
@lennysan on X
Tibo Sottiaux, Head of ChatGPT and Codex at OpenAI, shares his predictions from a conversation with Lenny Rachitsky: agents will soon handle most internet actions, the model picker will disappear, and today's clever agent scaffolding will become obsolete as models improve. He also covers what skills matter now, how OpenAI hires, and the burnout risk of running dozens of agents at once.
- Most internet actions will be taken by agents, and Notion's MCP server launch already showed how quickly agent traffic can strain a product's systems and economics.
- Tibo expects models to get dramatically better and cheaper, so he advises building as if they will be about 10 times better within a year, and he says his own forecast was too slow.
- Agent teams should grow and shrink with each model release, since a larger model can absorb tasks that once needed elaborate loops and graphs.
OpenAI announced GPT-Live-1, a voice API that lets AI agents listen and speak simultaneously for more natural conversations, plus rolled out developer features like customizable keyboard shortcuts, a skills system for Codex, and a multi-provider LLM spec called Open Responses.
- GPT-Live-1 handles simultaneous listening and speaking in a single model, reducing latency and letting users interrupt or add details mid-conversation without waiting for the AI to finish
- Codex now supports reusable skills (instruction bundles following the agentskills.io standard) that can be called directly or selected automatically based on user prompts
- Open Responses is an open-source spec for building multi-provider LLM interfaces, letting developers build agentic systems without rewriting code for each model
- New efficiency improvements include GPT-5-Codex-Mini for cost savings, 50% higher rate limits across ChatGPT tiers, and improved Git workflow integration in the editor
QuickReset AI tracks OpenAI's public Codex usage resets by monitoring Tibo's announcements and historical patterns, letting you see when resets happen and get email alerts before your allowance refreshes. It separates confirmed schedules, public signals, and historical forecasts so you can plan around rate limit resets without guessing.
- Tracks 26 weeks of Codex reset history with source-linked announcements from @tibo, showing direct resets (immediate refills) and banked resets (saved credits) separately
- Generates a daily forecast based on recent reset intervals and public signals, currently showing 35% chance for the next reset
- Sends email alerts when resets approach so you can use remaining allowance before limits refresh
- Only reports public bonus events and cannot trigger, grant, or sell resets — forecasts are estimates, not guarantees
@nifinet on X
A Sortlist exec walks through building a daily outbound pipeline on OpenAI's Codex CLI, using ChatGPT sign-in instead of a separate API key. Six file-based Codex jobs sense buying signals, score accounts, draft and check messages, log outcomes, and learn weekly from replies.
- Codex runs each step through codex exec against plain files (CSV in, JSON schemas out), with cron driving a morning shortlist and approval queue.
- The author argues timing beats volume: outbound should trigger on real events like a role opening, a funding round, or a team change, not on cold lists.
- Writing and checking are split into separate steps, and scheduled runs avoid approval prompts by keeping to files, shell, and APIs rather than interactive MCP calls.
- A weekly learning step reads outcomes and recommends retiring weak triggers and banning phrases, so the engine gets more selective over time.
Researchers at Tenet Security showed how anyone with a public Sentry DSN can inject a fake error report that coding agents like Claude Code, Cursor, and Codex will treat as a fix instruction. The agent fetches the malicious payload via the Model Context Protocol and runs arbitrary commands on the developer’s machine, exposing environment secrets and credentials. Sentry won’t close the write endpoint, leaving the fix to agent runtimes to filter untrusted data.
- A public write-only Sentry DSN lets attackers inject fake error reports that coding agents (Claude Code, Cursor, Codex) blindly treat as trusted fix instructions, leading to arbitrary code execution on developer machines.
- Tenet's tests across 2,388 organizations (including 71 Tranco top-1M sites) got an 85% success rate with 100+ confirmed code executions, hitting even a developer at a $250B Fortune 100 firm.
- The attack is invisible to traditional defenses (firewalls, EDR, WAFs, IAM) since it never touches victim infrastructure or needs passwords, and prompt-level "ignore untrusted data" instructions failed to stop it.
- Sentry isn't closing the vulnerable write endpoint, so the only real fix is runtime-level gating in the agent itself to sandbox or reject commands sourced from external/unauthenticated data.